---
license: mit
---
## Overview

**DeepSeek** developed and released the [DeepSeek R1 Distill Qwen 1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) model, a distilled version of the Qwen 1.5B language model. It is fine-tuned for high-performance text generation and optimized for dialogue and information-seeking tasks. This model achieves a balance of efficiency and accuracy while maintaining a smaller footprint compared to the original Qwen 1.5B.

The model is designed for applications in customer support, conversational AI, and research, prioritizing both helpfulness and safety.

## Variants

| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [gguf](https://huggingface.co/cortexso/deepseek-r1-distill-qwen-1.5b/tree/main) | `cortex run deepseek-r1-distill-qwen-1.5b` |


## Use it with Jan (UI)

1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
    ```text
    cortexso/deepseek-r1-distill-qwen-1.5b
    ```
## Use it with Cortex (CLI)

1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
    ```bash
    cortex run deepseek-r1-distill-qwen-1.5b
    ```
## Credits

- **Author:** DeepSeek
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
- **Original License:** [License](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B#7-license)
- **Papers:** [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://arxiv.org/html/2501.12948v1)